Recent works have shown that generative data augmentation, where synthetic samples generated from deep generative models are used to augment the training dataset, benefit certain NLP tasks. In this work, we extend this approach to the task of dialogue state tracking for goal-oriented dialogues, in which the data naturally exhibits a hierarchical structure over utterances and related annotations. Deep generative data augmentation for dialogue state tracking requires the generative model to be aware of the hierarchically structured data. We propose Variational Hierarchical Dialog Autoencoder (VHDA) for modeling various aspects of goal-oriented dialogues, including linguistic and underlying annotation structures. Our experiments show that our model is able to generate realistic and novel samples that improve the robustness of state-of-the-art dialogue state trackers, ultimately improving their final dialogue state tracking performances on several datasets.

本文提出了一种名为Variational Hierarchical Dialog Autoencoder（VHDA）的深度生成模型，用于goal-oriented dialogs的任务，它有效地捕获了不同层次和类型的dialog features之间的一致性，并且使用生成性数据增强方案，提高了下游目标跟踪器的鲁棒性，同时也在dialog response generation和user simulation方面具有良好表现。

基于变分分层对话自编码器的对话状态跟踪数据增强